HVE Core is a collection of agents, prompts, coding instructions, and skills for building repeatable software-development workflows with GitHub Copilot. It is intended for individuals and teams that want structured AI-assisted research, planning, implementation, and review, while the catalogue entries provide many of its reusable workflow components.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add microsoft/hve-core --skill rpi-plan-critiquegit clone --depth 1 https://github.com/microsoft/hve-coreWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/microsoft/hve-core/rpi-plan-critique)<a href="https://agentmods.dev/skills/microsoft/hve-core/rpi-plan-critique"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/rpi-plan-critique.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00036 | $0.01379 |
| Opus 5 | $0.00018 | $0.00690 |
| Sonnet 5 | $0.00007 | $0.00276 |
| Haiku 4.5 | $0.00004 | $0.00138 |
Grade A, and why
rpi-plan-critique scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RPI Plan Critique
Goal
Return a substantive, evidence-grounded credibility assessment of an RPI plan and its phase details. The critique is read-only with respect to plan sources and writes only the caller-specified critique artifact.
Flow
- Confirm the exact plan, phase-details, evidence, requirements, decisions, dependencies, acceptance criteria, and critique output path supplied by the caller.
- Read the supplied materials. Do not perform open-ended research or infer missing evidence as fact.
- Define the supplied inputs and criterion boundary, then assess the full boundary once across requirements, research, phases, tasks, acceptance criteria, dependencies, decisions, risks, and missed concerns. Return every actionable concern available from the supplied evidence in one complete finding set rather than serializing discoverable findings across critique passes.
- Write the critique using templates/plan-critique.md. Use severity-graded
PC-xxxfindings keyed to relevant requirement, research, phase, or task IDs. For each actionable finding, name the smallest useful change, action owner, exact resolving evidence, and whether it is a direct planner correction or needs a significant or divergent user decision. - Record critique execution as Complete, Partial, or Blocked, separately from the Pass, Revise, or Blocked verdict. A passing critique may identify residual risks that the planning parent has explicitly accepted.
Inputs
- Plan and phase-details paths
- Caller requirements and task context
- Supplied research, evidence pointers, draft details, and decisions
- Dependencies and acceptance criteria
- One critique output path
Success criteria
- The critique distinguishes evidence-backed concerns from missing evidence.
- Findings identify substantive gaps rather than structure, formatting, or cosmetic preferences.
- The critique records its inputs, criterion boundary, coverage assessment, and limitations.
- Each actionable finding has a severity, related IDs, evidence, impact, and smallest useful change.
- Each actionable finding identifies its action owner, exact resolving evidence, and whether it is a direct correction or requires a significant or divergent user decision.
- The critique returns one complete actionable finding set for the supplied boundary; cosmetic preferences and separately withheld late findings do not create serial passes.
- The closeout identifies the highest-impact finding, action owner, smallest next action, and whether a user response is required.
- The plan and phase-details sources remain unchanged.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 73 lines · 36 tokens per session scan A c943c68cd045
rpi-plan-critique is a skill published in the GitHub repository microsoft/hve-core (1,436 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 1,379 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…